Machine learning models for text and image processing

Document Type

Book Chapter

Publication Title

Machine Learning Models and Architectures for Biomedical Signal Processing

First Page

153

Last Page

177

Publisher

Elsevier

School

School of Engineering

RAS ID

77602

Comments

Soewu, T., Kaur, H., Sandhu, R., Sandhu, P., Ghai, D., Dhir, K., & Tripathi, S. L. (2025). Machine learning models for text and image processing. In Machine Learning Models and Architectures for Biomedical Signal Processing (pp. 153-177). Academic Press. https://doi.org/10.1016/B978-0-443-22158-3.00007-7

Abstract

The advent of Machine Learning (ML) techniques has rapidly improved the healthcare system over the past decade. Many health applications including biomedical signal processing require text and image processing. As per the concern for the performance of health-related applications, it is still a challenge. In today’s technological era, early-stage disease detection and relevant disease diagnosis have become urgent needs. ML models are tremendously useful in the preprocessing and implementation of text and image processing for better results. This chapter discusses the various preprocessing and performance-improving methods involved in text and image processing. The proposed work is configured to work for both text data processing and image processing. As per the concern for text-based inputs, the proposed model uses a sentiment analysis approach for data processing. Here, a hybrid model such as Recurrent Neural Network with Long-Short Term Memory is proposed for high accuracy in text data processing. Apart from this, for image processing, a novel Convolutional Neural Network approach is applied for brain tumor classification using Magnetic Resonance images. The proposed approach results in improved accuracy when compared to other architectures tested.

DOI

10.1016/B978-0-443-22158-3.00007-7

Access Rights

subscription content

Share

 
COinS